INDEX

Explanations

words and conjunctions that connect other words, and the letters "PPC"

oai_token-act-pair · gemini-2.0-flash

general descriptions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 morire

-0.63

guien

-0.60

 détru

-0.60

følgelig

-0.60

 découver

-0.58

 necessidades

-0.57

 tatuagem

-0.56

 antaranya

-0.56

ELTS

-0.55

BorderFactory

-0.55

POSITIVE LOGITS

 ControllerBase

0.58

the

0.58

ibat

0.55

tanleria

0.52

 فريبيس

0.52

 transférez

0.50

HttpPut

0.50

[])

0.49

 those

0.49

zaj

0.49

Activations Density 11.522%

words and conjunctions that connect other words, and the letters "PPC"

general descriptions

No Comments

No Known Activations